See every side of every news story
Published loading...Updated

Watch This: Google Genie 3 Can Create a 3D World, Let You Explore It, and Interact with It in Real Time

GOOGLE DEEPMIND RESEARCH LABS, AUG 5 – Genie 3 enhances AI training with real-time interaction and longer 3D environment simulations at 720p, extending interactive sessions from 20 seconds to several minutes, DeepMind says.

  • On Tuesday, Google DeepMind unveiled Genie 3, an AI program that generates 3D interactive worlds in real time from text prompts.
  • The release follows Genie 2 in December 2024, which produced 10 to 20 seconds of 360p environments, while Genie 3 extends interaction to several minutes at 720p.
  • Genie 3 lets users change the environment dynamically by typing new prompts, enabling actions like painting walls or adding characters, and supports real-time navigation and interaction.
  • DeepMind notes Genie 3 currently cannot simulate real-world locations perfectly and supports limited interaction time, but calls it a key step toward artificial general intelligence with some testers now accessing it.
  • DeepMind aims to expand tester access and sees Genie 3 as advancing AI training methods and potential applications in gaming, education, and embodied agent research.
Insights by Ground AI
Does this summary seem wrong?

37 Articles

Center

Generating video has already become outdated, now what it takes is to create interactive worlds where you are the protagonist, as Genie 3 from Google offers.

·Madrid, Spain
Read Full Article
Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • 50% of the sources are Center
50% Center

Factuality 

To view factuality data please Upgrade to Premium

Ownership

To view ownership data please Upgrade to Vantage

Engadget broke the news in United States on Tuesday, August 5, 2025.
Sources are mostly out of (0)